GPT-5.6 Luna Pro is described as the same underlying model as GPT-5.6 Luna, served with reasoning mode set to pro for higher-quality responses on complex tasks. It is listed as an OpenAI model under the id openai/gpt-5.6-luna-pro.
OpenAI’s documentation describes Luna as the cost-sensitive, high-volume GPT-5.6 tier, and separate guidance says pro mode performs more model work before returning a single final answer.
| Developer | Open AI |
|---|---|
| Model ID | openai/gpt-5.6-luna-pro |
| Release Date | July 8, 2026 |
| Context Window | 1,050,000 tokens (~1.1M) |
| Max Output Tokens | 128,000 tokens |
| Modalities | Image, Text → Text |
| Capabilities | file input, parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, vision |
Pro reasoning mode
The model uses reasoning.mode set to pro for higher-quality responses on complex tasks.
Underlying model
It is the same underlying model as GPT-5.6 Luna.
OpenAI API listing
OpenAI’s API documentation includes GPT-5.6 Luna as a named model, and third-party model listings identify the Pro variant by the exact id openai/gpt-5.6-luna-pro.
Higher-quality complex-task behavior
The pro configuration is described as doing more model work for difficult tasks before producing its final answer.
Complex task handling
Suitable for requests where additional model work is preferred to improve answer quality on harder problems.
High-volume workloads
The Luna tier is described as cost-sensitive and high-volume, making the Pro configuration relevant when that tier is needed with pro reasoning.
Single final-answer workflows
OpenAI’s pro mode guidance describes returning one final answer after additional internal work.
GPT-5.6 Luna
The base Luna model is the same underlying model without the pro reasoning mode.
GPT-5.6 Terra
OpenAI positions Terra as a separate GPT-5.6 tier alongside Luna.
GPT-5.6 Sol
OpenAI positions Sol as another GPT-5.6 tier alongside Luna and Terra.
Sources: https://medium.com/@techlatest.net/gpt-5-6-models-explained-sol-vs-terra-vs-luna-pro-models-features-which-one-should-you-choose-6693668917f7 · https://openai.com/index/gpt-5-6/ · https://developers.openai.com/api/docs/models/gpt-5.6-luna
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
GPT-5.6 Luna Pro is documented as suited for high-volume API workloads like summarization, classification, and data extraction. It is also suited for long-context document Q&A and legal or medical record analysis. Another documented use case is vision-enabled agents that parse screenshots, charts, and PDFs. It is also described as useful for coding assistance and multi-file repository reasoning.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-5.6-luna-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "openai/gpt-5.6-luna-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-5.6-luna-pro","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
GPT-5.6 Luna Pro has documented cache-write billing at 1.25× the uncached input token rate, and prompts with more than 272K input tokens are billed at 2× input and 1.5× output for the full request.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-5.6 Luna Pro This page | Agentic workflows and structured output |
GPT-5.6 Luna Pro has a 1,050,000 tokens context window and can return up to 128,000 tokens.
GPT-5.6 Luna Pro takes image, text as input and returns text.
Use openai/gpt-5.6-luna-pro as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
GPT-5.6 Luna Pro became available on July 9, 2026.
GPT-5.6 Luna Pro is priced at input $0.27508 / 1M tokens, output $1.65048 / 1M tokens, cached input $0.027508 / 1M tokens.
Yes, GPT-5.6 Luna Pro can stream responses as they are generated.
Yes, GPT-5.6 Luna Pro accepts image input alongside text.
GPT-5.6 Luna Pro was built by OpenAI.
Yes, it supports tools including parallel tool calls.
